• 한국가구학회지
• /
• 제23권3호
• /
• pp.317-323
• /
• 2012

Indoor of 21th century information-oriented society is feeling necessity of emotional design that can satisfy emotional of human. Desire of modern becomes various and emotional lighting design is risen on important element in indoor plan on human oriented modern society who become complicated. Emotional space is trend that is atomized as go today and is expanded as the target and area also go. That is, is included as target of emotional space to light and sound, taste, smack and is appealing by senses of human. Wish to do color that is optical element among element of senses differently and present design. Design concept of this research is emotional lighting design that can receive. It is lighting that equip emotional beauty and ability from modern indoor improving space. I wish to quote emotional lighting design about effect gotten to indoor by sight of designer.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.137-138
• /
• 1998

The purpose of this study is to evaluate the HRV(Heart Rate Variability) to visual and auditory stimulation. We analysed psychological effect and HRV of music, light, and music with light. The results show that HRV pattern is significantly related to the psychological effect, and HRV spectrum is useful to extract more information when various stimulation are presented.

• 한국지능시스템학회논문지
• /
• 제2권3호
• /
• pp.50-57
• /
• 1992

Neural networks have become more popular recently and are now being applied to numerous fiedls. One of the major applications of neural networks is image recognition. Various image recognition system have been proposed so far, but there is no definite solution yet. In this paper, we propose a design of Fuzzy Neural Network Image Recognizer(FNNIR). Our model uses a fuzzy neural network model, named SONN[KIM90]. This model returns the information of the number of clusters and cluster and cluster center values for a given image data ste. Unlike the well-kinwn backpropagation technique, we do not need retraining for new data. Our newly designed image recongitionsystem FNNIR that uses fuzzy merger is proposed and experimented for a sample color image.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제26권1호
• /
• pp.150-150
• /
• 1999

In this paper, a content-based image retrieval scheme based on scale-space theory is proposed. The existing methods using scale-space theory consider all scales for image retrieval,thereby requiring a lot of computation. To overcome this problem, the proposed algorithm utilizes amodified histogram intersection method to select candidate images from database. The relative scalebetween a query image and a candidate image is calculated by the ratio of histograms. Feature pointsare extracted from the candidates using a corner detection algorithm. The feature vector for eachfeature point is composed of RGB color components and differential invariants. For computing thesimilarity between a query image and a candidate image, the euclidean distance measure is used. Theproposed image retrieval method has been applied to various images and the performance improvementover the existing methods has been verified.

• 정보처리학회논문지B
• /
• 제16B권2호
• /
• pp.117-122
• /
• 2009

명함을 이용한 전세계적인 고객 관리 시스템을 구축하기 위해 다국어 명함인식기를 개발하였다. 먼저 다양한 언어의 문자인식 및 학습을 위해 Unicode 기반 문자 이미지 DB를 구축하였으며, 다양한 입력 장치를 통해 획득한 명함 영상에 대하여 정확한 데이터를 얻기 위한 다양한 컬러영상 처리 기술이 적용되었다. 다음에 다층 퍼셉트론 신경망, 언어 유형별 개별 문자인식, 각 언어별 명함에 사용된 필드별 키워드 DB를 이용한 후처리를 적용하여 명함 인식률을 향상시켰다.

• ETRI Journal
• /
• 제34권3호
• /
• pp.429-438
• /
• 2012

This study presents two reversible data hiding schemes based on the coefficient shifting (CS) algorithm. The first scheme uses the CS algorithm with a mean predictor in the spatial domain to provide a large payload while minimizing distortion. To guard against manipulations, the second scheme uses a robust version of the CS algorithm with feature embedding implemented in the integer wavelet transform domain. Simulations demonstrate that both the payload and peak signal-to-noise ratio generated by the CS algorithm with a mean predictor are better than those generated by existing techniques. In addition, the marked images generated by the variant of the CS algorithm are robust to various manipulations created by JPEG2000 compression, JPEG compression, noise additions, (edge) sharpening, low-pass filtering, bit truncation, brightness, contrast, (color) quantization, winding, zigzag and poster edge distortion, and inversion.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.11-15
• /
• 2020

In a typical initial setup of a PCB component inspection system, operators should manually input various information such as category, position, and inspection area for each component to be inspected, thus causing much inconvenience and longer setup time. Although there are many deep learning based object detectors, RetinaNet is regarded as one of best object detectors currently available. In this paper, a method using an extended RetinaNet is proposed that automatically detects its component category and position for each component mounted on PCBs from a high-resolution color input image. We extended the basic RetinaNet feature pyramid network by adding a feature pyramid layer having higher spatial resolution to the basic feature pyramid. It was demonstrated by experiments that the extended RetinaNet can detect successfully very small components that could be missed by the basic RetinaNet. Using the proposed method could enable automatic generation of inspection areas, thus considerably reducing the setup time of PCB component inspection systems.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2005년도 하계학술대회 논문집 Vol.6
• /
• pp.497-499
• /
• 2005

A portable terminal assistant market grows rapidly every year and it requires many change in research on display devices. Among many newly developing methods, OLED(Organic Light Emitting Diode) is considered an advanced flat display device because its excellent characteristics, including high speed response, full color performance, low power consumption and flux of panel. However changes in the market of display shows that the market will require 3-dimensional images, but it is hard for existing 2-dimensional displays to make 3-dimensional images. Therefore we will try to find various methods such as holograms. In this paper, we will show existing flat displays can make 3-dimensional images by applying Lenticular Screen printing techniques on the organic semiconductor display device.

• 건축역사연구
• /
• 제30권1호
• /
• pp.33-42
• /
• 2021

This paper analysed the architectural images on Pleasant Gathering of Leeum, Samsung museum of art, which has been assumed as a work of the Koryo dynasty. Through the comparison between the unique wooden structure at roof edge on the building images and real architectures, it found the buildings on the painting were from China Fujian(福建), not from Korea. It also analysed the color painting on buildings, trees, themes from previous famous paintings and dresses to confirm these images were came from the early period of the Ming dynasty. It is a very unique painting containing various information on the Fujian ancient architecture, but its architecture drawing is not as skillful as typical ancient Chinese paintings.

• 펄프종이기술
• /
• 제48권1호
• /
• pp.134-141
• /
• 2016

Dampening in printing is not only used with plain water but also used with various substances like dampening additive, in order to improve the wetting property by lowering the surface tension and to control material for modifing the ink transfer characteristic with proper emulsification. We have studied the printing quality according to these, looking into interrelationship among the dampening solution's pH, electrical conductivity and IPA content, prescribing the proper usage and minimum usage of fountain solution and dampening additive. In this study, it shows good result when mixing at the 7 wt% dampening with additive solution, which is result from the color density of printed sheets in accordance with the change of dampening solution condition. And the printed density value calculated 1 hour after printing, it shows relatively safe value at the etch liquid 4 wt% and IPA addition 2 wt%. The dry down at this test showed similar results regardless of various dampening conditions on coated paper, but in case of uncoated paper, the dry down showed a quite gap of different due to the fast penetration to the paper.